Mohammed Akour et al., International Journal of Advanced Trends in Computer Science and Engineering, 8(5),September - October 2019, 2231 - 2235 2231 ABSTRACT Predicting Activities of Daily Living (ADL) for elder people could let them live actively, independently and healthy. In this paper, Authors perform a comparative study to address the effectiveness of deep learning algorithms on ADL. As a baseline structure, The Convolutional Neural Networks (CNN's) as a deep learning algorithm is employed to perform the experiments and conducting the comparative study with the very common used traditional machine learning algorithms. Several factors in the CNN are manipulated to gain the best result in predicting the ADL in comparison with the most ML result in this matter. To reduce the threat to validity, very common data set are used in several previous studies in term of ADL prediction is adopted in this paper. The dataset was collected from a wearable chest accelerometer. The total numbers of participants are 15 and they were performing 7 main activities namely standing up, working at the computer, going up downstairs, standing, walking, walking and talking with someone and talking while standing, walking and going up downstairs. Three experiments were conducted in this paper, and CNN provides promising result in term of ADL predictions for the very common data set in this field and ML algorithms. Key words: Machine Learning, Classification, Pattern Recognition, Activity Recognition, ADL, deep learning algorithms. . 1. INTRODUCTION Elder people can be more susceptible to life accident and many diseases such as Osteoarthritis, diabetes and other diseases. Many healthcare companies aim to provide several mechanisms to help elder people by supporting them to do all daily living activities in easy way. Although, the daily activities of elder people are known, health care services and researchers address and investigate their daily living activities. In which inclusive perception of ADL could lead to grasping their requirements and mitigate the challenges that they face through their lives. The competence to automatically infer and monitor infer human actions in naturalistic environments is fundamental for many applications in wide range of areas such as energy management, context-aware personal assistance and healthcare. Latterly, wearable cameras such as the GoPro 1 and Narrative 2 enable capturing human actions and behaviors [1]. Deep learning algorithms allow computational models to learn data representations with various levels of abstraction. These methods can dramatically improve the state of the art in speech recognition, object detection, object recognition, and many other domains like drug discovery and genomics. Deep learning detect complicated structure in large datasets by using the backpropagation algorithms to determine how a machine change its internal parameters that are used to compute data representation in each layer from the data representation in the previous layer. Deep convolutional nets have brought about breakthroughs in image processing, whereas recurrent nets have shown light on sequential data such as speech and text [12]. The goal of this work is to evaluate and compare the efficiency of deep learning algorithms in classifying and predicting collected dataset of ADL data from a wearable accelerometer. The comparison is conducted against very well-known Machine learning algorithms using the same data set. Section II summarizes some related works, Section III presents deep learning algorithms that are used in this study, Section IV describes the research methodology, and Section V concludes the paper. 2. RELATED WORK Activities of Daily Living are the activities that people perform during their day, such as showering, wearing, eating working and other activities [2]. Authors in [3] Studied the The Effectiveness of Using Deep Learning Algorithms in Predicting Daily Activities Mohammed Akour 1 , Osama Al Qasem 2 , Hiba Alsghaier 3 , Khalid Al-Radaideh 4 1 Computer Engineering Department, Al Yamamah University, Saudi Arabia 1,2,3 Information Systems Department, Yarmouk University, Jordan 4 Qassim University, Saudi Arabia m_akour@yu.edu.sa ISSN 2278-3091 Volume 8, No.5, September - October 2019 International Journal of Advanced Trends in Computer Science and Engineering Available Online at http://www.warse.org/IJATCSE/static/pdf/file/ijatcse57852019.pdf https://doi.org/10.30534/ijatcse/2019/57852019